How Social Media Algorithms Actually Work (And How to Beat Them)

[00:01] media algorithm. If you want to get more views with less effort, it's critical you understand how the algorithms actually work. And once you learn this, I guarantee you will never look at content the same way again. In this

[00:13] social algorithms work, why they pick certain videos to push over others, and the specific things you can do to make them prioritize your content. Now, this information is based on a ton of outlier data and comments made by the Instagram

[00:28] CEO himself. So, this is the latest and greatest for what's actually working right now. If you just follow this, your content will perform way better. By the Callaway. I have a million followers, I've done billions of views, and content

[00:40] is all I do all day long. All right, first, let's just start with how the algorithms actually work. And this is actually super helpful to understand. Once you hear it, it'll make a lot of sense. Social media companies only have

[00:52] one goal, to keep people on the platform as long as possible. When people stay companies make more money. It's as simple as that. Now, to keep you on the platform longer, they do their best to serve you the content they think you'll

[01:05] enjoy the most. And that means the algorithm is just one giant matchmaker. does a good job with this matching, you're going to keep watching and stay. But if it starts doing a bad job and it shows you stuff you don't want to watch,

[01:19] sounds simple, but this is how social algorithms work in a nutshell. Now, here's why this matters for you. If you want to hijack the algorithm and make it push your video more, all you have to do is help it make better matches with your

[01:32] content. [music] So, in this video, I'm going to explain exactly how to do that. algo hack you could ever learn. Okay, now here's how this matchmaking process actually works under the hood, so we can understand exactly what to do to

[01:45] manipulate it. When you post a video on social media, the very first thing the platform does is analyze what that video is about. I call this a digital fingerprint. Now, this analysis is multimodal, so it's watching your video

[01:57] with computer vision to understand what's going on visually. It's listening to get a better understanding of the transcript and what's actually being said, and it's also reading all the metadata, the caption, the hashtag, the

[02:11] creator, the location, anything else it can find. It then combines all that information together in real time to build a single contextual understanding of the video. This is called a topic mapping. Now, based on that topic

[02:23] mapping, the algorithm builds a fit score, which is its prediction for who it thinks will best like this video. So, at this point, you've posted it, it's anyone yet. So, we're ready to start showing the video to people. But, this

[02:37] obviously the algorithm doesn't just blast your video off to millions of people right off the bat, or you'd have millions of views. This is what actually goes on under the hood. The algorithm uses its fit score to pick roughly 200

[02:50] people to show the video to first. This is called the initial sample test group. If it could rank all 100 million people that are on the app at one time, this is the group of 200 people it thinks will like the video the most. Now, very

[03:04] important, of these 200 people, most of them are non-followers, because the algorithm wants to test how well strangers react to your video. It knows already follow you, but if strangers like it, too, well, then that means this

[03:17] is a really good video. This is why when people say followers don't matter don't matter in the sampling process, because most of those 200 people are Now, based on the metrics from this initial sample group of 200 people, the

[03:31] algorithm is going to get positive, neutral, or negative data back. Essentially, of those 200, how many of them liked and watched the video? What was the set of data? If the data is positive, that means the algorithm's

[03:43] guess of the fit score was accurate. And so, it knows exactly what type of person to push the video to further. The next time it pushes, let's say it's 2,000 people. And if that's good, then it's 20,000 people. And if that's good, then

[03:56] it's 200,000 people. And it just keeps going until the data starts coming back weaker. Now, if the original data was neutral, kind of good, kind of bad, the algorithm will redo its fit score and push the video again. But this time,

[04:08] only to maybe another group of 200. It doesn't go crazy to 20,000. It just resamples. If the data is negative right off the bat with those 200, well then the algo's going to tighten up and stop pushing almost immediately. And again,

[04:21] it slows down that push because it doesn't want to risk alienating people because they see a bad video. So, if you're in the 200 view jail, or you post a video and it flops, what this really means is that the algorithm got bad data

[04:35] back from that initial sample group of 200. Now, one more thing before we move on this. The reason why even million view banger videos eventually slow down is because even those run out of people that want to watch it. The data gets

[04:48] eventually it starts to fade off. So, in a nutshell, this is how social algorithms actually work under the hood. This is what happens when you go to post a video. You post it, it does the topic mapping, it samples with a group of

[05:01] roughly 200 people, and then it either boosts, retries, or stops immediately based on how the sample data comes back. So, what does all this actually mean for happening under the hood, how can you best adjust your content strategy to

[05:15] take advantage and get the algorithm to push you more? That's what we're going push you more? That's what we're going to go through right now. get more views, you only need to do two things. Number one is to help the

[05:28] algorithm build a better fit score, so that it finds the best possible sample group of 200 people to go to first. And then number two is to make sure that sample group actually likes and engages with your video. Because if the sample

[05:40] actually like your video, well then you're going to be in great shape because the algo will get amazing data back and just [music] keep boosting you going to do now is break down the tactics for how to trigger both of those

[05:53] things. Helping find the right sample group, and then helping make sure that sample group engages well. This is essentially the systematic process for activating the algorithm and getting it to work for you. Now, if you like how

[06:05] like a scientific and psychology perspective, I actually just published a free guide doing the same thing for my entire content system. It's from ideas Science-based and data-backed. This is the exact content system I ran last year

[06:21] views and millions in profit from content. It's also the same thing I install with business owners when I work with them one-on-one. Completely free, my gift to you. You can get it below or at the link shortformsytem.co.

[06:34] What can you do to help the algorithm build a better fit score and find a stronger sample group for your video? Here's the answer, very simple. All you have to do is consistently make videos

[06:46] about the same topic for the same audience avatar over and over and over. You want to become intentionally precise and narrow with the topics you pick and how you position. Here's why. After a few similar videos in a row, the

[07:00] algorithm will start to understand that your channel talks about X topic for Y avatar profile. It will then have built sample groups for all those previous videos and have a very clear understanding of who to go back to from

[07:13] an avatar perspective. The more this avatar group is the same over time, the more confident the algorithm can be when it dials this in. Now, this process of consistently making videos about the same few topics for the same avatar is

[07:26] called audience matching. And if there's one content principle I swear by, it's this. When you make videos for lots of different topics for several different avatars, the sample data comes back mixed and the algorithm gets confused.

[07:38] When it's confused, it pushes your video less because it doesn't want to risk bad fits to bad viewers. For example, imagine you made three videos. One on trends, and then the next one on politics. The algorithm would have no

[07:52] be about. And because of this, it three videos it should model its fit score after. So, let's say your fourth trends. Chances are the algorithm's going to build a blended fit score

[08:06] across those first three videos. A little bit of people from tech, a little little bit of people from politics. Not literally those people, but influence from who liked those videos. And when it does this, the fit score targeting for

[08:19] your fourth video is going to be a mix of all three. And so, when it pushes it, of course, the sample data for the health trends video that also has tech and politics type viewers is going to come back weak. This will result almost

[08:31] certainly in your video flopping. What this means in simple terms is that if you want to help the algorithm find the right sample group and build a better fit score, you got to keep your topics and audience selection narrow

[08:43] consistently. And this means sometimes saying no to ideas that seem viral, but would resonate with the wrong audience. Even one viral hit to an audience outside of your core demo will result in the next several videos having poor

[08:57] sample data because it confuses the algorithm. This discipline in topic and and typically beginners that are starting out are spraying and praying this. Okay, so that's one side of the equation. Very simply, just narrow your

[09:11] topic and audience, and your sample fit will go up. Now, on the other side of making sure, once you have that sample, that it actually engages well with your video. And that means they watch it, they like it, they save it, they share

[09:24] engagement metrics, as many as we can possibly get. >> So, what can we do on this side to make sure that initial sample data from these people comes back strong? Well, when the algorithm's gauging if it's strong or

[09:37] not, it's really only looking at three core metrics. The first one is average watch time. How long did someone watch in a number of seconds per video? And also, by proxy, percent completion. What percent of the video was completed on

[09:49] average? The second metric is engagement rate. So, this is likes plus comments plus shares divided by views. And the third, which is really important and nobody can access, is called watch time session share. In a session for a

[10:01] minutes, how many of those 60 were spent watching your videos? That percentage is access this anywhere, but it's a critical metric that social algorithms >> [music] >> So, the million-dollar question for you

[10:16] is how can you improve these metrics? What can you do in your video to make data comes back clean, so that it just pushes your video to more people? Well, a short, cheeky answer is if you want the metrics to go up, you just make

[10:29] stronger hooks, better storytelling, and more interesting visuals, obviously. there anything tactical you can do at a studs level to increase the you watch this channel a lot, you

[10:44] There's only four things you need to do to make your video better so that that >> [music] >> Number one is that the topic needs to be relevant for the ideal viewer. This is obvious, and it goes with the first

[10:56] piece I said. What you cover has to actually solve a problem that they have. If that's the case, engagement will go up. Number two, the information you share needs to be both non-obvious and tactically implementable. Is it new

[11:09] they actually use it to solve that problem? If those things are true, the engagement rate will go up. Number three, the viewer has to actually have a high absorption of the information you say. It could be on target and

[11:22] understand what you're saying, then they can't apply it. So, if they could apply then number four, there needs to be a short distance to implement your implementable means they can take a little bit of action and get a big

[11:37] result based on your promise. Now, you won't typically hear people frame it in this way, but if your content has those four attributes, I guarantee you're have higher engagement, the data comes back more positive, they push it to more

[11:49] of the people, those people are people you want, and the flywheel spins. What this really means, those four things in layman's terms, you got to cover a core pain point or problem they have. You got to have something useful or interesting

[12:01] to say. You got to say it in a way they can actually understand, and they have to be able to take what you say and apply it on their own. Those are the four horsemen to driving good video performance. If you do this, you're set,

[12:14] and that's really all you need to hijack the algorithm to push you more. Pick an avatar, stick to it, narrow your topic selection, and then drive those four sample group will stay dialed, and they'll all engage with the video at a

[12:27] high rate. Incidentally, these four factors are also how you turn viewers into buyers. If you want people to buy, those four components also make sense to like the core DNA if you're trying to build a money machine with content. Now,

[12:40] I'll say this, the easiest way to make sure you're picking the right topics that actually work for your avatar group is to just study the videos that are already working in your niche. It shocks me how few people actually do this, but

[12:53] in sandcastles.ai, you can build a group of competitor channels that are already crushing, and just filter by outlier score to see all the best performing videos. There's now this feature where if you save the video to library, you

[13:07] can see all the attributes. I'm talking transcript, topic, the exact hook, the about the video that drove the curiosity. You can then take that, remix there. So, all you need to do if you're confused on which topics to pick for

[13:23] sandcastles and use this resource. It shocks me how few people are using data basically guarantees that you're serving the right stuff to your audience. Now, before I end this video, I just want to include one more bonus topic around the

[13:38] is a little bit theoretical, hopefully it made sense, hopefully it helped you, you have action items to work on. But, I just want to include one more thing at a tactical level that you can take away and really hammer value from this video.

[13:50] Another way to drive algorithmic push is to increase the number of comments on your video. Most people know this. There are five things you can do tactically to increase the number of comments you're getting. Number one is to take a hard

[14:02] stance on your topic. People typically comment when they violently agree or disagree, mostly disagree, with whatever your stance is or perspective. If you play the middle and hedge, you're going to get fewer comments. So, I recommend

[14:15] you pick a side, pro or con, and that will drive comments. [music] Number two contrarian side. Like I said, people love to comment when they disagree, when contrarian side, that means you think the majority of people are wrong, which

[14:29] majority of people will want to comment because they disagree with you. If you create more enemies, you drive more comments. Tip number three is to amplify the stance you take by ratcheting up the way you frame your points. If you said

[14:42] something like, "This is the best way to cook pasta." versus, "This pasta is shops in the world." Which one is going to drive a more violent discussion in the comments? The more extreme version, of course, always is. So, that's how you

[14:56] is to build your topics around cult-loved brands, people, ideas, and things people already have made up their opinion on, the faster they're willing

[15:08] to jump into the comments, especially if they disagree. For example, if you take category of shoes, more people will have they like or dislike Nike, and it will trigger them to comment. Tip number five

[15:20] is to position your take or stance to drive significant emotion. The more your video, the more they're going to feel compelled to want to comment. Now, those five things around comment, that was just a little extra sprinkle to give

[15:33] you more tactics on how to drive activation and engagement to make the algorithm push you. All of those feed back to picking the right topic for the point on what I just went through. Hopefully that's helpful and you can put

[15:46] I've got for this video. As a recap, we covered a lot of ground. We really broke algorithms work and how you theoretically and fundamentally can hijack them to push your videos more. I tried my best to kind of demystify this

[16:01] black box and give you tactics that you can use to your advantage. As always, give you perspectives that most people don't cover in a tactical bite-size way you typically see about the algorithm is talking about settings, hacks, or these

[16:16] little caption tweaks. None of that stuff actually works. If you think that video again. Posting time does not matter. Hashtags in your captions don't matter. The captions themselves don't matter. The only thing that matters is

[16:29] making great videos for a specific avatar group across a narrow band of topics over and over and over. That's the only thing that matters. That is the cake. Everything else is the icing. Focus on the cake. As a reminder, if you

[16:41] want access to my full content system, this is the exact blueprint I use with my own team. How I find ideas, how I write hooks, how I validate these things, how I do research, my entire funnel to turn viewers into dollars,

[16:53] below for free, my gift to you, shortformsytem.co. And if you have any other topics around social media growth, around content and content systems that you want me to cover or that you feel blocked on, just

[17:06] comments to inform the database of videos that we make next. So, anything the comments. It will help greatly to inform what we should make. All right, guys. That's all we've got. We will see you on the next video. Peace.